RefineBench

non-profit

AI & ML interests

None defined yet.

Recent Activity

passing2961 authored a paper about 18 hours ago

Meta$^n$: Recursive Self-Improvement through Emergent Depth

passing2961 authored a paper about 18 hours ago

AssurAI: Experience with Constructing Korean Socio-cultural Datasets to Discover Potential Risks of Generative AI

passing2961 authored a paper about 2 months ago

Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks

View all activity

authored 2 papers about 18 hours ago

Meta$^n$: Recursive Self-Improvement through Emergent Depth

Paper • 2608.24735 • Published 2 days ago • 10

AssurAI: Experience with Constructing Korean Socio-cultural Datasets to Discover Potential Risks of Generative AI

Paper • 2511.20686 • Published Nov 20, 2025

authored a paper about 2 months ago

Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks

Paper • 2606.29082 • Published Jun 27 • 43

submitted a paper to Daily Papers about 2 months ago

Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks

Paper • 2606.29082 • Published Jun 27 • 43

authored a paper 2 months ago

Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

Paper • 2606.18216 • Published Jun 16 • 65

submitted a paper to Daily Papers 2 months ago

Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

Paper • 2606.18216 • Published Jun 16 • 65

authored a paper 2 months ago

Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation

Paper • 2605.11651 • Published May 13

authored a paper 3 months ago

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Paper • 2606.13673 • Published Jun 11 • 112

authored 2 papers 3 months ago

Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization

Paper • 2605.26457 • Published May 26 • 7

K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts

Paper • 2606.02404 • Published Jun 1 • 59

submitted a paper to Daily Papers 3 months ago

K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts

Paper • 2606.02404 • Published Jun 1 • 59

authored a paper 3 months ago

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

Paper • 2605.28774 • Published May 27 • 93

authored a paper 3 months ago

On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists

Paper • 2605.20668 • Published May 20 • 13

submitted a paper to Daily Papers 3 months ago

On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists

Paper • 2605.20668 • Published May 20 • 13

authored 2 papers 4 months ago

Reasoning over mathematical objects: on-policy reward modeling and test time aggregation

Paper • 2603.18886 • Published Mar 19 • 6

Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs

Paper • 2605.09063 • Published May 9 • 82

authored a paper 6 months ago

Recursive Think-Answer Process for LLMs and VLMs

Paper • 2603.02099 • Published Mar 2 • 7

submitted a paper to Daily Papers 6 months ago

Recursive Think-Answer Process for LLMs and VLMs

Paper • 2603.02099 • Published Mar 2 • 7

authored a paper 8 months ago

Masking Teacher and Reinforcing Student for Distilling Vision-Language Models

Paper • 2512.22238 • Published Dec 23, 2025 • 30

submitted a paper to Daily Papers 8 months ago

Masking Teacher and Reinforcing Student for Distilling Vision-Language Models

Paper • 2512.22238 • Published Dec 23, 2025 • 30